{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:59Z","timestamp":1778048339339,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00322","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3297-3309","source":"Crossref","is-referenced-by-count":0,"title":["VOCAL: Visual Odometry via ContrAstive Learning"],"prefix":"10.1109","author":[{"given":"Chi-Yao","family":"Huang","sequence":"first","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeel","family":"Bhatt","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yezhou","family":"Yang","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"ref3","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"CoRR"},{"key":"ref4","first-page":"4","article-title":"Factor graphs and gtsam: A hands-on introduction","volume":"2","author":"Dellaert","year":"2012","journal-title":"Georgia Institute of Technology, Tech. Rep"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"ref6","article-title":"Direct sparse odometry","author":"Engel","year":"2016","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref9","author":"Gong","year":"2022","journal-title":"Ranksim: Ranking similarity regularization for deep imbalanced regression"},{"key":"ref10","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"CoRR"},{"key":"ref11","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019","journal-title":"CoRR"},{"key":"ref12","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","author":"Jing","year":"2021","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979949"},{"key":"ref18","article-title":"Undeepvo: Monocular visual odometry through unsupervised deep learning","author":"Li","year":"2017","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref21","author":"Achiam","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2018.2853729"},{"key":"ref23","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"CoRR"},{"key":"ref24","first-page":"27","article-title":"Label ranking methods based on the plackett-luce model","author":"Ranking","year":"2010","journal-title":"Poster presented at ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.178"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2307\/1422689"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00619"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"ref32","author":"Anil","year":"2025","journal-title":"Gemini: A family of highly capable multimodal models"},{"key":"ref33","article-title":"DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras","author":"Teed","year":"2021","journal-title":"CoRR"},{"key":"ref34","volume-title":"Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)","author":"Thrun","year":"2005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00143"},{"key":"ref36","article-title":"Trajectory regularization enhances self-supervised geometric representation","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref38","article-title":"Tartanvo: A generalizable learning-based VO","author":"Wang","year":"2020","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0786"},{"key":"ref43","author":"Zhan","year":"2021","journal-title":"Df-vo: What should be learnt for visual odometry?"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_42"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492180.pdf?arnumber=11492180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:52Z","timestamp":1778046892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00322","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}